Transparency and validation of vehicle locomotive actions
A system includes one or more processors that obtaining data from one or more source. The data includes an ongoing or planned locomotive action and contextual information associated with the locomotive action. The processors also synchronize the data, generate an output comprising textual components, and convert the output. The processors may execute the locomotive action which may include a driving action.
1 . A system comprising:
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the system to perform:
obtaining data from one or more sources, wherein the data comprises or identifies an ongoing or planned locomotive action and contextual information associated with the locomotive action,
synchronizing the data, wherein synchronizing the data comprises inferring one or more intents associated with the vehicle or the ongoing or planned locomotive action based on the contextual information, the contextual information comprising a type of vehicle associated with the ongoing or planned locomotive action and a relative orientation of the vehicle with respect to other occupants;
generating an output comprising textual components, wherein the output comprises a version of the synchronized data; and
converting the output into a converted output, wherein the converted output comprises a condensed version of the output.
2 . The system of claim 1 , wherein the contextual information comprises an event or a stimulus that triggered the ongoing or planned locomotive action.
3 . The system of claim 1 , wherein the contextual information comprises information of an external entity that is external to the system, an internal component that is internal to the system, or a change of an environmental condition.
4 . The system of claim 3 , wherein the contextual information comprises information regarding a potential malfunction of the internal component; and the data comprises a planned locomotive action indicating to reduce a speed or to stop.
5 . The system of claim 1 , wherein the contextual information comprises information from a perception model, a planning model, a prediction model, a localization model, or a control model.
6 . The system of claim 1 , wherein the instructions further cause the system to perform:
executing the planned locomotive action; and
monitoring one or more attributes of the system during the executing of the locomotive action.
7 . The system of claim 1 , wherein the converting of the output comprises selectively removing portions of the generated output based on respective priorities.
8 . The system of claim 1 , wherein the obtaining of the data comprises obtaining packets from the one or more sources, the synchronizing of the data comprises synchronizing respective payloads of the packets, and the generating of the output comprises generating a new packet having the output within a payload of the new packet.
9 . The system of claim 1 , wherein the obtaining of the data comprises obtaining fused sensor data from different sensor modalities.
10 . The system of claim 1 , wherein the converting of the output is performed by a machine learning component, the machine learning component comprising a large language model (LLM).
11 . The system of claim 1 , wherein the planned locomotive action is based on signaling of an external entity, and an inferred intent of the external entity.
12 . The system of claim 1 , wherein the planned locomotive action is based on a presence of an external entity, the external entity including a non-terrestrial entity.
13 . The system of claim 1 , wherein the planned locomotive action is based on a presence of a non-vehicular entity.
14 . The system of claim 1 , wherein the planned locomotive action is based on a behavior or a predicted behavior of an external entity.
15 . The system of claim 1 , wherein the planned locomotive action is based on a presence or an absence of equipment or accessories attached to an external entity.
16 . The system of claim 1 , wherein the planned locomotive action is based on a road geometry.
17 . The system of claim 1 , wherein the contextual information identifies whether the type of the vehicle is an authority vehicle, and the relative orientation of the vehicle identifies whether the vehicle is travelling along an intended direction of travel.
18 . A method comprising:
obtaining data from one or more sources, wherein the data comprises or identifies an ongoing or planned locomotive action and contextual information associated with the locomotive action,
synchronizing the data, wherein synchronizing the data comprises inferring one or more intents associated with the vehicle or the ongoing or planned locomotive action based on the contextual information, the contextual information comprising a type of vehicle associated with the ongoing or planned locomotive action and a relative orientation of the vehicle with respect to other occupants;
generating an output comprising textual components, wherein the output comprises a version of the synchronized data; and
converting the output into a converted output, wherein the converted output comprises a condensed version of the output.
19 . The method of claim 18 , wherein the contextual information comprises an event or a stimulus that triggered the ongoing or planned locomotive action.
20 . The method of claim 19 , wherein the contextual information comprises information regarding a potential malfunction of the internal component; and the data comprises a planned locomotive action indicating to reduce a speed or to stop.